Assessing the accuracy and consistency of ChatGPT in clinical pharmacy management: A preliminary analysis with clinical pharmacy experts worldwide

Comparative evaluation of artificial intelligence systems' accuracy in providing medical drug dosages: A methodological study

BACKGROUND

Medication errors, especially in dosage calculation, pose risks in healthcare. Artificial intelligence (AI) systems like ChatGPT and Google Bard may help reduce errors, but their accuracy in providing medication information remains to be evaluated.

AIM

To evaluate the accuracy of AI systems (ChatGPT 3.5, ChatGPT 4, Google Bard) in providing drug dosage information per Harrison's Principles of Internal Medicine.

METHODS

A set of natural language queries mimicking real-world medical dosage inquiries was presented to the AI systems. Responses were analyzed using a 3-point Likert scale. The analysis, conducted with Python and its libraries, focused on basic statistics, overall system accuracy, and disease-specific and organ system accuracies.

RESULTS

ChatGPT 4 outperformed the other systems, showing the highest rate of correct responses (83.77%) and the best overall weighted accuracy (0.6775). Disease-specific accuracy varied notably across systems, with some diseases being accurately recognized, while others demonstrated significant discrepancies. Organ system accuracy also showed variable results, underscoring system-specific strengths and weaknesses.

CONCLUSION

ChatGPT 4 demonstrates superior reliability in medical dosage information, yet variations across diseases emphasize the need for ongoing improvements. These results highlight AI's potential in aiding healthcare professionals, urging continuous development for dependable accuracy in critical medical situations.

Performance of ChatGPT on Factual Knowledge Questions Regarding Clinical Pharmacy

ChatGPT is a language model that was trained on a large dataset including medical literature. Several studies have described the performance of ChatGPT on medical exams. In this study, we examine its performance in answering factual knowledge questions regarding clinical pharmacy. Questions were obtained from a Dutch application that features multiple-choice questions to maintain a basic knowledge level for clinical pharmacists. In total, 264 clinical pharmacy-related questions were presented to ChatGPT and responses were evaluated for accuracy, concordance, quality of the substantiation, and reproducibility. Accuracy was defined as the correctness of the answer, and results were compared to the overall score by pharmacists over 2022. Responses were marked concordant if no contradictions were present. The quality of the substantiation was graded by two independent pharmacists using a 4-point scale. Reproducibility was established by presenting questions multiple times and on various days. ChatGPT yielded accurate responses for 79% of the questions, surpassing pharmacists' accuracy of 66%. Concordance was 95%, and the quality of the substantiation was deemed good or excellent for 73% of the questions. Reproducibility was consistently high, both within day and between days (>92%), as well as across different users. ChatGPT demonstrated a higher accuracy and reproducibility to factual knowledge questions related to clinical pharmacy practice than pharmacists. Consequently, we posit that ChatGPT could serve as a valuable resource to pharmacists. We hope the technology will further improve, which may lead to enhanced future performance.

Assessing accuracy of ChatGPT in response to questions from day to day pharmaceutical care in hospitals

Background

The advent of Large Language Models (LLMs) such as ChatGPT introduces opportunities within the medical field. Nonetheless, use of LLM poses a risk when healthcare practitioners and patients present clinical questions to these programs without a comprehensive understanding of its suitability for clinical contexts.

Objective

The objective of this study was to assess ChatGPT's ability to generate appropriate responses to clinical questions that hospital pharmacists could encounter during routine patient care.

Methods

Thirty questions from 10 different domains within clinical pharmacy were collected during routine care. Questions were presented to ChatGPT in a standardized format, including patients' age, sex, drug name, dose, and indication. Subsequently, relevant information regarding specific cases were provided, and the prompt was concluded with the query "what would a hospital pharmacist do?". The impact on accuracy was assessed for each domain by modifying personification to "what would you do?", presenting the question in Dutch, and regenerating the primary question. All responses were independently evaluated by two senior hospital pharmacists, focusing on the availability of an advice, accuracy and concordance.

Results

In 77% of questions, ChatGPT provided an advice in response to the question. For these responses, accuracy and concordance were determined. Accuracy was correct and complete for 26% of responses, correct but incomplete for 22% of responses, partially correct and partially incorrect for 30% of responses and completely incorrect for 22% of responses. The reproducibility was poor, with merely 10% of responses remaining consistent upon regeneration of the primary question.

Conclusions

While concordance of responses was excellent, the accuracy and reproducibility were poor. With the described method, ChatGPT should not be used to address questions encountered by hospital pharmacists during their shifts. However, it is important to acknowledge the limitations of our methodology, including potential biases, which may have influenced the findings.

Appropriateness of ChatGPT as a resource for medication-related questions

With its increasing popularity, healthcare professionals and patients may use ChatGPT to obtain medication-related information. This study was conducted to assess ChatGPT's ability to provide satisfactory responses (i.e., directly answers the question, accurate, complete and relevant) to medication-related questions posed to an academic drug information service. ChatGPT responses were compared to responses generated by the investigators through the use of traditional resources, and references were evaluated. Thirty-nine questions were entered into ChatGPT; the three most common categories were therapeutics (8; 21%), compounding/formulation (6; 15%) and dosage (5; 13%). Ten (26%) questions were answered satisfactorily by ChatGPT. Of the 29 (74%) questions that were not answered satisfactorily, deficiencies included lack of a direct response (11; 38%), lack of accuracy (11; 38%) and/or lack of completeness (12; 41%). References were included with eight (29%) responses; each included fabricated references. Presently, healthcare professionals and consumers should be cautioned against using ChatGPT for medication-related information.

Poor performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal dysfunction

PURPOSE

Clinical decision support systems (CDSS) are used to identify drugs with potential need for dose modification in patients with renal impairment. ChatGPT holds the potential to be integrated in the electronic health record (EHR) system to give such dosing advices. In this study, we aim to evaluate the performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal impairment.

METHODS

This cross-sectional study was performed at Tergooi Medical Center, the Netherlands. CDSS alerts regarding renal dysfunction were collected from the electronic health record (EHR) during a 2-week period and were presented to ChatGPT and an expert panel. Alerts were presented with and without patient variables. To evaluate the performance, suggested medication interventions were compared.

RESULTS

In total, 172 CDDS alerts were generated for 80 patients. Indecisive responses by ChatGPT to alerts were excluded. For alerts presented without patient variables, ChatGPT provided "correct and identical" responses to 19.9%, "correct and different" responses to 26.7%, and "incorrect responses to 53.4% of the alerts. For alerts including patient variables, ChatGPT provided "correct and identical" responses to 16.7%, "correct and different" responses to 16.0%, and "incorrect responses to 67.3% of the alerts. Accuracy was better for newer drugs such as direct oral anticoagulants.

CONCLUSION

The performance of ChatGPT in clinical rule-guided dose interventions in hospitalized patients with renal dysfunction was poor. Based on these results, we conclude that ChatGPT, in its current state, is not appropriate for automatic integration into our EHR to handle CDSS alerts related to renal dysfunction.

Is ChatGPT reliable and accurate in answering pharmacotherapy-related inquiries in both Turkish and English?

INTRODUCTION

Artificial intelligence (AI), particularly ChatGPT, is becoming more and more prevalent in the healthcare field for tasks such as disease diagnosis and medical record analysis. The objective of this study is to evaluate the proficiency and accuracy of ChatGPT in different domains of clinical pharmacy cases and queries.

METHODS

The study NAPLEX® Review Questions, 4th edition, pertaining to 10 different chronic conditions compared ChatGPT's responses to pharmacotherapy cases and questions obtained from McGraw Hill's, alongside the answers provided by the book's authors. The proportion of correct responses was collected and analyzed using the Statistical Package for the Social Sciences (SPSS) version 29.

RESULTS

When tested in English, ChatGPT had substantially higher mean scores than when tested in Turkish. The average accurate score for English and Turkish was 0.41 ± 0.49 and 0.32 ± 0.46, respectively, p = 0.18. Responses to queries beginning with "Which of the following is correct?" are considerably more precise than those beginning with "Mark all the incorrect answers?" 0.66 ± 0.47 as opposed to 0.16 ± 0.36; p = 0.01 in English language and 0.50 ± 0.50 as opposed to 0.14 ± 0.34; p < 0.05in Turkish language.

CONCLUSION

ChatGPT displayed a moderate level of accuracy while responding to English inquiries, but it displayed a slight level of accuracy when responding to Turkish inquiries, contingent upon the question format. Improving the accuracy of ChatGPT in languages other than English requires the incorporation of several components. The integration of the English version of ChatGPT into clinical practice has the potential to improve the effectiveness, precision, and standard of patient care provision by supplementing personal expertise and professional judgment. However, it is crucial to utilize technology as an adjunct and not a replacement for human decision-making and critical thinking.

Assessing the applicability and appropriateness of ChatGPT in answering clinical pharmacy questions

OBJECTIVES

Clinical pharmacists rely on different scientific references to ensure appropriate, safe, and cost-effective drug use. Tools based on artificial intelligence (AI) such as ChatGPT (Generative Pre-trained Transformer) could offer valuable support. The objective of this study was to assess ChatGPT's capacity to correctly respond to clinical pharmacy questions asked by healthcare professionals in our university hospital.

MATERIAL AND METHODS

ChatGPT's capacity to respond correctly to the last 100 consecutive questions recorded in our clinical pharmacy database was assessed. Questions were copied from our FileMaker Pro database and pasted into ChatGPT March 14 version online platform. The generated answers were then copied verbatim into an Excel file. Two blinded clinical pharmacists reviewed all the questions and the answers given by the software. In case of disagreements, a third blinded pharmacist intervened to decide.

RESULTS

Documentation-related issues (n=36) and drug administration mode (n=30) were preponderantly recorded. Among 69 applicable questions, the rate of correct answers varied from 30 to 57.1% depending on questions type with a global rate of 44.9%. Regarding inappropriate answers (n=38), 20 were incorrect, 18 gave no answers and 8 were incomplete with 8 answers belonging to 2 different categories. No better answers than the pharmacists were observed.

CONCLUSIONS

ChatGPT demonstrated a mitigated performance in answering clinical pharmacy questions. It should not replace human expertise as a high rate of inappropriate answers was highlighted. Future studies should focus on the optimization of ChatGPT for specific clinical pharmacy questions and explore the potential benefits and limitations of integrating this technology into clinical practice.

Accuracy of GPT-4 in histopathological image detection and classification of colorectal adenomas

AIMS

To evaluate the accuracy of Chat Generative Pre-trained Transformer (ChatGPT) powered by GPT-4 in histopathological image detection and classification of colorectal adenomas using the diagnostic consensus provided by pathologists as a reference standard.

METHODS

A study was conducted with 100 colorectal polyp photomicrographs, comprising an equal number of adenomas and non-adenomas, classified by two pathologists. These images were analysed by classic GPT-4 for 1 time in October 2023 and custom GPT-4 for 20 times in December 2023. GPT-4's responses were compared against the reference standard through statistical measures to evaluate its proficiency in histopathological diagnosis, with the pathologists further assessing the model's descriptive accuracy.

RESULTS

GPT-4 demonstrated a median sensitivity of 74% and specificity of 36% for adenoma detection. The median accuracy of polyp classification varied, ranging from 16% for non-specific changes to 36% for tubular adenomas. Its diagnostic consistency, indicated by low kappa values ranging from 0.06 to 0.11, suggested only poor to slight agreement. All of the microscopic descriptions corresponded with their diagnoses. GPT-4 also commented about the limitations in its diagnoses (eg, slide diagnosis best done by pathologists, the inadequacy of single-image diagnostic conclusions, the need for clinical data and a higher magnification view).

CONCLUSIONS

GPT-4 showed high sensitivity but low specificity in detecting adenomas and varied accuracy for polyp classification. However, its diagnostic consistency was low. This artificial intelligence tool acknowledged its diagnostic limitations, emphasising the need for a pathologist's expertise and additional clinical context.

Utilizing ChatGPT in Telepharmacy

BACKGROUND

ChatGPT is an artificial intelligence-powered chatbot that has demonstrated capabilities in numerous fields, including medical and healthcare sciences. This study evaluates the potential for ChatGPT application in telepharmacy, the delivering of pharmaceutical care via means of telecommunications, through assessing its interactions, adherence to instructions, and ability to role-play as a pharmacist while handling a series of life-like scenario questions.

METHODS

Two versions (ChatGPT 3.5 and 4.0, OpenAI) were assessed using two independent trials each. ChatGPT was instructed to act as a pharmacist and answer patient inquiries, followed by a set of 20 assessment questions. Then, ChatGPT was instructed to stop its act, provide feedback and list its sources for drug information. The responses to the assessment questions were evaluated in terms of accuracy, precision and clarity using a 4-point Likert-like scale.

RESULTS

ChatGPT demonstrated the ability to follow detailed instructions, role-play as a pharmacist, and appropriately handle all questions. ChatGPT was able to understand case details, recognize generic and brand drug names, identify drug side effects, interactions, prescription requirements and precautions, and provide proper point-by-point instructions regarding administration, dosing, storage and disposal. The overall means of pooled scores were 3.425 (0.712) and 3.7 (0.61) for ChatGPT 3.5 and 4.0, respectively. The rank distribution of scores was not significantly different (P>0.05). None of the answers could be considered directly harmful or labeled as entirely or mostly incorrect, and most point deductions were due to other factors such as indecisiveness, adding immaterial information, missing certain considerations, or partial unclarity. The answers were similar in length across trials and appropriately concise. ChatGPT 4.0 showed superior performance, higher consistency, better character adherence and the ability to report various reliable information sources. However, it only allowed an input of 40 questions every three hours and provided inaccurate feedback regarding the number of assessed patients, compared to 3.5 which allowed unlimited input but was unable to provide feedback.

CONCLUSIONS

Integrating ChatGPT in telepharmacy holds promising potential; however, a number of drawbacks are to be overcome in order to function effectively.

ChatGPT and Clinical Training: Perception, Concerns, and Practice of Pharm-D Students

Background

The emergence of Chat-Generative Pre-trained Transformer (ChatGPT) by OpenAI has revolutionized AI technology, demonstrating significant potential in healthcare and pharmaceutical education, yet its real-world applicability in clinical training warrants further investigation.

Methods

A cross-sectional study was conducted between April and May 2023 to assess PharmD students' perceptions, concerns, and experiences regarding the integration of ChatGPT into clinical pharmacy education. The study utilized a convenient sampling method through online platforms and involved a questionnaire with sections on demographics, perceived benefits, concerns, and experience with ChatGPT. Statistical analysis was performed using SPSS, including descriptive and inferential analyses.

Results

The findings of the study involving 211 PharmD students revealed that the majority of participants were male (77.3%), and had prior experience with artificial intelligence (68.2%). Over two-thirds were aware of ChatGPT. Most students (n= 139, 65.9%) perceived potential benefits in using ChatGPT for various clinical tasks, with concerns including over-reliance, accuracy, and ethical considerations. Adoption of ChatGPT in clinical training varied, with some students not using it at all, while others utilized it for tasks like evaluating drug-drug interactions and developing care plans. Previous users tended to have higher perceived benefits and lower concerns, but the differences were not statistically significant.

Conclusion

Utilizing ChatGPT in clinical training offers opportunities, but students' lack of trust in it for clinical decisions highlights the need for collaborative human-ChatGPT decision-making. It should complement healthcare professionals' expertise and be used strategically to compensate for human limitations. Further research is essential to optimize ChatGPT's effective integration.